Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety profile is covered structurally. The description adds real behavioral context — that request bodies must match a schema discovered from another tool, and that accounts returns 'available_actions' — but says nothing about response shape, pagination, rate limits, or what happens when the body deviates from the step-2 schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the workflow position and the word REQUIRED, then enumerates prerequisites as a numbered list and closes with the schema-fidelity instruction. It is compact and ordered by execution sequence; minor waste in repeating 'using query_contexts' across both enumerated steps.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single opaque nested-body parameter with an output schema present (so return values need not be described), the description supplies the missing procedural context: where workspace_id/brand_id/account_id come from, where the body schema comes from, and which actions are common. The main residual gap is the absence of any failure-mode or body-validation guidance if the agent skips the prerequisite steps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is one required parameter, 'body', typed as a free-form nested object with additionalProperties:true and 0% schema description coverage — the schema itself conveys almost nothing. The description partially compensates by naming the common actions (report/integrated/get/, ad/get/, campaign/get/, adgroup/get/, advertiser/info/) and by instructing the agent to follow the step-2 schema, but it never explains the fields inside body.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Query TikTok Ads data') and situates it precisely as 'Step 3 (FINAL) of workflow', which is enough for an agent to know it is the execution terminal of a three-step pipeline. It does not distinguish itself from the sibling 'execute_action', so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names prerequisite calls to the sibling query_contexts (request='accounts', then request='actions_details' with a concrete action list) and marks them REQUIRED before this tool can be used. It also lists the common action values that end up in the body, so the agent knows how to proceed rather than guessing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.